Span-based Semantic Parsing for Compositional Generalization

TL;DR

This paper introduces SpanBasedSP, a span-based semantic parser that improves compositional generalization over seq2seq models by explicitly modeling partial program compositions, showing significant gains on challenging datasets.

Contribution

The paper proposes SpanBasedSP, a span-based parser that predicts span trees and enhances compositional generalization in semantic parsing tasks.

Findings

Significant accuracy improvement on compositional splits (from 61.0% to 88.9%).

Performs comparably to seq2seq models on standard splits.

Effectively models non-projective trees with extended CKY.

Abstract

Despite the success of sequence-to-sequence (seq2seq) models in semantic parsing, recent work has shown that they fail in compositional generalization, i.e., the ability to generalize to new structures built of components observed during training. In this work, we posit that a span-based parser should lead to better compositional generalization. we propose SpanBasedSP, a parser that predicts a span tree over an input utterance, explicitly encoding how partial programs compose over spans in the input. SpanBasedSP extends Pasupat et al. (2019) to be comparable to seq2seq models by (i) training from programs, without access to gold trees, treating trees as latent variables, (ii) parsing a class of non-projective trees through an extension to standard CKY. On GeoQuery, SCAN and CLOSURE datasets, SpanBasedSP performs similarly to strong seq2seq baselines on random splits, but dramatically improves performance compared to baselines on splits that require compositional generalization: from $61.0 \rightarrow 88.9$ average accuracy.